Beyond Weighted Summation: Learnable Nonlinear Aggregation Functions for Robust Artificial Neurons

ArXi:2603.19344v1 Announce Type: cross Weighted summation has remained the default input aggregation mechanism in artificial neurons since the earliest neural network models. While computationally efficient, this design implicitly behaves like a mean-based estimator and is therefore sensitive to noisy or extreme inputs. This paper investigates whether replacing fixed linear aggregation with learnable nonlinear alternatives can improve neural network robustness without sacrificing trainability. Two differentiable aggregation mechanisms are.